Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ClawCap/ManoBrowser --skill platform-data-explorergit clone --depth 1 https://github.com/ClawCap/ManoBrowserWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/clawcap/manobrowser/platform-data-explorer)<a href="https://agentmods.dev/skills/clawcap/manobrowser/platform-data-explorer"><img src="https://agentmods.dev/badge/skills/clawcap/manobrowser/platform-data-explorer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/clawcap/manobrowser/platform-data-explorer"><img src="https://agentmods.dev/badge/skills/clawcap/manobrowser/platform-data-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.03470 |
| Opus 5.5 | $0.00035 | $0.01388 |
| Sonnet 5.5 | $0.00017 | $0.00694 |
| Haiku 4.5 | $0.00009 | $0.00347 |
Grade A, and why
platform-data-explorer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
平台探索与 Skill 发现
概述
这是一个探索型 Meta-skill:给定任意平台 URL 或功能模块,使用 DataSaver 工具系统性探索该平台,分析出可以做哪些 Skill(操作类 + 取数类),生成 Skill 提案清单供用户选择,用户确认后按类型分流调用对应的创建 skill:
- API 取数类 → 调用
api-skill-builder(逆向 API → 生成取数 Skill) - 浏览器操作类 → 调用
chrome-workflow-build(执行并记录 → 生成操作 Skill)
输入:平台 URL / 模块名称 / 功能描述 输出:Skill 提案清单(含优先级、可行性评估、实现方案)
执行流程
Phase 1: 平台侦察(了解平台全貌)
↓
Phase 2: 功能模块发现(逐个模块探索)
↓
Phase 3: Skill 可行性评估(每个潜在 Skill 的技术方案)
↓
Phase 4: 输出提案清单(供用户确认)
↓
Phase 5: 用户确认后,按类型分流创建 Skill
Phase 1: 平台侦察
目标:了解平台整体结构、技术栈、主要功能模块。
Step 1.1: 打开目标页面
工具: chrome_navigate
参数:
url: {target_url}
active: true
⚠️
active: true很重要,某些 SPA 平台(如灵犀)在后台标签页不加载数据。
Step 1.2: 页面结构分析
工具: chrome_get_document
观察并记录:
- 平台名称和类型(数据平台 / 内容平台 / 电商 / 工具类)
- 技术栈(React / Vue / Angular / jQuery)
- 导航结构(侧边栏菜单 / 顶部Tab / 面包屑)
- 是否需要登录
- 主要功能入口有哪些
Step 1.3: 导航菜单提取
// 提取平台的导航菜单结构
(() => {
// 尝试多种常见导航结构
const navSelectors = [
'nav a', '.sidebar a', '.menu a', '.nav-item a',
'[class*="menu"] a', '[class*="nav"] a', '[class*="sidebar"] a',
'.ant-menu a', '.el-menu a', // Ant Design / Element UI
];
const links = new Set();
const menuItems = [];
navSelectors.forEach(sel => {
document.querySelectorAll(sel).forEach(a => {
const text = a.textContent.trim();
const href = a.getAttribute('href') || '';
const key = text + '|' + href;
if (text && text.length < 30 && !links.has(key)) {
links.add(key);
menuItems.push({ text, href, visible: a.offsetParent !== null });
}
});
});
return JSON.stringify({
totalMenuItems: menuItems.length,
items: menuItems.slice(0, 50)
}, null, 2);
})()
Step 1.4: API 与资源分析
// 发现平台加载了哪些 API 和资源
(() => {
const resources = performance.getEntriesByType('resource');
const apis = resources
.filter(r => r.initiatorType === 'xmlhttprequest' || r.initiatorType === 'fetch')
.map(a => {
const url = new URL(a.name);
return { path: url.pathname, params: url.search.substring(0, 80) };
});
// 去重,按路径分组
const apiGroups = {};
apis.forEach(a => {
const base = a.path.replace(/\/\d+/g, '/{id}'); // 归一化数字ID
if (!apiGroups[base]) apiGroups[base] = { path: a.path, count: 0 };
apiGroups[base].count++;
});
return JSON.stringify({
totalAPIs: apis.length,
uniqueAPIs: Object.keys(apiGroups).length,
apiList: Object.values(apiGroups).slice(0, 30)
}, null, 2);
})()
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 363 lines · 87 tokens per session scan A e82e6c780842
platform-data-explorer is a skill published in the GitHub repository ClawCap/ManoBrowser (9 stars, last pushed 6mo ago), licensed MIT. It adds 87 tokens to every session and 3,470 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
xiaohongshu-ops
A browser-based operations assistant for Xiaohongshu, a Chinese social-media and shopping platform. It uses a logged-in Chrome browser to analyse accounts and content and manage publishing workflows.
aipex-browser
AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating pages, clicking elements, filling forms, capturing screenshots, managing tabs, or downloading content — by connecting to the AIPex MCP bridge.
browser-relay
Operate the user's existing, logged-in Chrome locally or on an explicitly connected remote machine. Read complete page content with actionable refs and links, perform grouped actions, and use screenshots in persistent browser sessions. Skip static public pages and pure REST APIs.
browser-bridge
Token-efficient Chrome tab inspection, interaction, and patching via local bridge extension (CLI: bbx). Reads live DOM, styles, console, network, and storage from a real Chrome tab with lower token cost than screenshots.
just-scrape
Search, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON from a site, crawl documentation or site sections, monitor a page for changes, inspect request history, check ScrapeGraph…
control-chrome
Control and inspect the user's real Google Chrome through byob's local MCP tools. Use when Claude Code must work with an existing signed-in browser session, open or navigate tabs, understand a rendered page, click or type in web UI, fill forms, capture screenshots, inspect console or network activity, download page…